Building system with multi-tiered model based optimization for ventilation and setpoint control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building systems face challenges in simultaneously optimizing indoor air quality (IAQ) and energy consumption, as ventilation actions that improve IAQ often lead to energy inefficiency, and existing solutions require significant computing resources, making real-time optimization on edge devices difficult.
Innovation Solution
A multi-tiered optimization approach using sequence-to-sequence neural networks, specifically long-short term memory (LSTM) networks, to predict and optimize ventilation and temperature setpoints based on building data, decoupling IAQ and energy optimizations to reduce computing complexity and enable real-time decision-making on low-capacity devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ventilation actions are increased to improve indoor air quality, then IAQ is improved, but energy consumption increases
Solution Approach 1:
The patent segments the control problem into two independent optimizations: first optimizing ventilation actions for IAQ, then optimizing temperature setpoints for energy consumption. This decoupling allows each optimization to focus on its specific objective without the computational complexity of joint optimization, while still achieving overall system performance improvement.
Solution Approach 2:
The patent performs preliminary optimization of ventilation actions to achieve optimal IAQ before proceeding to optimize temperature setpoints for energy efficiency. This sequential approach ensures that IAQ requirements are met first, then energy optimization is applied within the constraints established by the ventilation decisions.
2Reliability
If joint optimization of ventilation and temperature setpoints is performed, then both IAQ and energy consumption are optimized, but computing resources required increase significantly
Solution Approach 1:
The patent divides the complex joint optimization problem into two simpler, sequential optimization tasks: (1) optimize ventilation actions for IAQ, and (2) optimize temperature setpoints for energy consumption given the ventilation decisions. This segmentation reduces computational complexity while maintaining optimization effectiveness.
Solution Approach 2:
The patent extracts and separates the ventilation optimization from the temperature setpoint optimization, treating them as independent sub-problems. By taking out the ventilation optimization first and fixing it, the subsequent temperature optimization becomes simpler and requires fewer computing resources.
3Measurement precision
If complex optimization models are used to simultaneously optimize multiple parameters, then optimization accuracy improves, but real-time control capability decreases
Solution Approach 1:
The patent segments the optimization into two rapid, sequential steps that can be executed in real-time. Each step focuses on a single objective (IAQ then energy), reducing computational burden while maintaining sufficient accuracy for practical control applications.
Solution Approach 2:
The patent performs preliminary optimization of ventilation actions before optimizing temperature setpoints. This preliminary action establishes constraints and initial conditions that simplify the second optimization step, enabling real-time execution while maintaining accuracy.
Data Source
AI summary
A building system operates to receive building data for a building describing one or more conditions of the building and perform a first optimization with a multi-tiered model that predicts a first condition of the building based on a first control setting, the first optimization determining one or more first values of the first control setting. The building system operates to perform a second optimization with the multi-tiered model that predicts a second condition of the building based on a second control setting and the one or more first values of the first control setting, the second optimization determining one or more second values of the second control setting and operate building equipment based on the one or more first values of the first control setting and the one or more second values of the second control setting.